What is the price for objectivity

I knew I had to remake this chart.

The simple message of this chart is hidden behind layers of visual complexity. What the analyst wants readers to focus on (as discerned from the text on the right) is the red line, the seven-day moving average of new hospital admissions due to Covid-19 in Texas.

My eyes kept wandering away from the line. It's the sideway data labels on the columns. It's the columns that take up vastly more space than the red line. It's the sideway date labels on the horizontal axis. It's the redundant axis labels for hospitalizations when the entire data set has already been printed. It's the two hanging diamonds, for which the clues are filed away in the legend above.

Here's a version that brings out the message: after Phase 2 re-opening, the number of hospital admissions has been rising steadily.

Dots are used in place of columns, which push these details to the background. The line as well as periods of re-opening are directly labeled, removing the need for a legend.

Here's another visualization:

This chart plots the weekly average new hospital admissions, instead of the seven-day moving average. In the previous chart, the raggedness of moving average isn't transmitting any useful information to the average reader. I believe this weekly average metric is easier to grasp for many readers while retaining the general story.

***

On the original chart by TMC, the author said "the daily hospitalization trend shows an objective view of how COVID-19 impacts hospital systems." Objectivity is an impossible standard for any kind of data analysis or visualization. As seen above, the two metrics for measuring the trend in hospitalizations have pros and cons. Even if one insists on using a moving average, there are choices of averaging methods and window sizes.

Scientists are trained to believe in objectivity. It frequently disappoints when we discover that the rest of the world harbors no such notion. If you observe debates between politicians or businesspeople or social scientists, you rarely hear anyone claim one analysis is more objective - or less subjective - than another. The economist who predicts Dow to reach a new record, the business manager who argues for placing discounted products in the front not the back of the store, the sportscaster who maintains Messi is a better player than Ronaldo: do you ever hear these people describe their methods as objective?

Pursuing objectivity leads to the glorification of data dumps. The scientist proclaims disinterest in holding an opinion about the data. This is self-deception though. We clearly have opinions because when someone else  "misinterprets" the data, we express dismay. What is the point of pretending to hold no opinions when most of the world trades in opinions? By being "objective," we never shape the conversation, and forever play defense.

Designs of two variables: map, dot plot, line chart, table

The New York Times found evidence that the richest segments of New Yorkers, presumably those with second or multiple homes, have exited the Big Apple during the early months of the pandemic. The article (link) is amply assisted by a variety of data graphics.

The first few charts represent different attempts to express the headline message. Their appearance in the same article allows us to assess the relative merits of different chart forms.

First up is the always-popular map.

The advantage of a map is its ease of comprehension. We can immediately see which neighborhoods experienced the greater exoduses. Clearly, Manhattan has cleared out a lot more than outer boroughs.

The limitation of the map is also in view. With the color gradient dedicated to the proportions of residents gone on May 1st, there isn't room to express which neighborhoods are richer. We have to rely on outside knowledge to make the correlation ourselves.

The second attempt is a dot plot.

We may have to take a moment to digest the horizontal axis. It's not time moving left to right but income percentiles. The poorest neighborhoods are to the left and the richest to the right. I'm assuming that these percentiles describe the distribution of median incomes in neighborhoods. Typically, when we see income percentiles, they are based on households, regardless of neighborhoods. (The former are equal-sized segments, unlike the latter.)

This data graphic has the reverse features of the map. It does a great job correlating the drop in proportion of residents at home with the income distribution but it does not convey any spatial information. The message is clear: The residents in the top 10% of New York neighborhoods are much more likely to have left town.

In the following chart, I attempted a different labeling of both axes. It cuts out the need for readers to reverse being home to not being home, and 90th percentile to top 10%.

The third attempt to convey the income--exit relationship is the most successful in my mind. This is a line chart, with time on the horizontal axis.

The addition of lines relegates the dots to the background. The lines show the trend more clearly. If directly translated from the dot plot, this line chart should have 100 lines, one for each percentile. However, the closeness of the top two lines suggests that no meaningful difference in behavior exists between the 20th and 80th percentiles. This can be conveyed to readers through a short note. Instead of displaying all 100 percentiles, the line chart selectively includes only the 99th , 95th, 90th, 80th and 20th percentiles. This is a design choice that adds by subtraction.

Along the time axis, the line chart provides more granularity than either the map or the dot plot. The exit occurred roughly over the last two weeks of March and the first week of April. The start coincided with New York's stay-at-home advisory.

This third chart is a statistical graphic. It does not bring out the raw data but features aggregated and smoothed data designed to reveal a key message.

I encourage you to also study the annotated table later in the article. It shows the power of a well-designed table.

[P.S. 6/4/2020. On the book blog, I have just published a post about the underlying surveillance data for this type of analysis.]

 

 

Hope and reality in one Georgia chart

Over the weekend, Georgia's State Health Department agitated a lot of people when it published the following chart:

(This might have appeared a week ago as the last date on the chart is May 9 and the title refers to "past 15 days".)

They could have avoided the embarrassment if they had read my article at DataJournalism.com (link). In that article, I lay out a set of the "unspoken conventions," things that visual designers are, or should be, doing more or less in their sleep. Under the section titled "Order", I explain the following two "rules":

• Place values in the natural order when it is available
• Retain the same order across all plots in a panel of charts

In the chart above, the natural order for the horizontal (time) axis is time running left to right. The order chosen by the designer  is roughly but not precisely decreasing height of the tallest column in each daily group. Many observers suggested that the columns were arranged to give the appearance of cases dropping over time.

Within each day, the counties are ordered in decreasing number of new cases. The title of the chart reads "number of cases over time" which sounds like cumulative cases but it's not. The "lead" changed hands so many times over the 15 days, meaning the data sequence was extremely noisy, which would be unlikely for cumulative cases. There are thousands of cases in each of these counties by May. Switching the order of the columns within each daily group defeats the purpose of placing these groups side-by-side.

Responding to the bad press, the department changed the chart design for this week's version:

This chart now conforms to the two spoken rules described above. The time axis runs left to right, and within each group of columns, the order of the counties is maintained.

The chart is still very noisy, with no apparent message.

***

Next, I'd like to draw your attention to a Data issue. Notice that the 15-day window has shifted. This revised chart runs from May 2 to May 16, which is this past Saturday. The previous chart ran from Apr 26 to May 9. 

Here's the data for May 8 and 9 placed side by side.

There is a clear time lag of reporting cases in the State of Georgia. This chart should always exclude the last few days. The case counts keep going up until it stabilizes. The same mistake occurs in the revised chart - the last two days appear as if new cases have dwindled toward zero when in fact, it reflects a lag in reporting.

The disconnect between the Question being posed and the quality of the Data available dooms this visualization. It is not possible to provide a reliable assessment of the "past 15 days" when during perhaps half of that period, the cases are under-counted.

***

This graphical distortion due to "immature" data has become very commonplace in Covid-19 graphics. It's similar to placing partial-year data next to full-year results, without calling out the partial data.

The following post from the ancient past (2005!) about a New York Times graphic shows that calling out this data problem does not actually solve it. It's a less-bad kind of thing.

The coronavirus data present more headaches for graphic designers than the financial statistics. Because of accounting regulations, we know that only the current quarter's data are immature. For Covid-19 reporting, the numbers are being adjusted for days and weeks.

Practically all immature counts are under-estimates. Over time, more cases are reported. Thus, any plots over time - if unadjusted - paint a misleading picture of declining counts. The effect of the reporting lag is predictable, having a larger impact as we run from left to right in time. Thus, even if the most recent data show a downward trend, it can eventually mean anything: down, flat or up. This is not random noise though - we know for certain of the downward bias; we just don't know the magnitude of the distortion for a while.

Another issue that concerns coronavirus reporting but not financial reporting is inconsistent standards across counties. Within a business, if one were to break out statistics by county, the analysts would naturally apply the same counting rules. For Covid-19 data, each county follows its own set of rules, not just  how to count things but also how to conduct testing, and so on.

Finally, with the politics of re-opening, I find it hard to trust the data. Reported cases are human-driven data - by changing the number of tests, by testing different mixes of people, by delaying reporting, by timing the revision of older data, by explicit manipulation, ...., the numbers can be tortured into any shape. That's why it is extremely important that the bean-counters are civil servants, and that politicians are kept away. In the current political environment, that separation between politics and statistics has been breached.

***

Why do we have low-quality data? Human decisions, frequently political decisions, adulterate the data. Epidemiologists are then forced to use the bad data, because that's what they have. Bad data lead to bad predictions and bad decisions, or if the scientists account for the low quality, predictions with high levels of uncertainty. Then, the politicians complain that predictions are wrong, or too wide-ranging to be useful. If they really cared about those predictions, they could start by being more transparent about reporting and more proactive at discovering and removing bad accounting practices. The fact that they aren't focused on improving the data gives the game away. Here's a recent post on the politics of data.

 

How Covid-19 deaths sneaked into Florida's statistics

Like many others, some Floridians are questioning their state's Covid statistics. It's clear there are numerous "degrees of freedom" for politicians to manipulate the numbers. What's not clear is who's influencing these decisions. Are they public-health experts, donors, voters, or whom?

A Twitter follower sent in the following chart, embedded in an informative article in Sun-Sentinel:

I like the visual design. It's clean, and conveys a moderately complex concept effectively. The reader may not immediately get what metrics are being plotted but the idea that the blue line should operate within the gray area.. until it doesn't is easily grasped. The range is technically an uncertainty band.

The metric is the proportion of total deaths (all causes) that are attributed to pneumonia and flu. Typical influenza deaths are found in that category. This chart investigates whether there were excess (unexplained) P&F deaths. The gray band measures the variability in the proportions of past years. When the blue line operates inside the band, the metric is normal. When it pierces the upper band, which happened here around week 25, a rare event has occurred.

The concern on Twitter was about the horizontal axis. Those integer labels can be confusing. The designer places a "how to read this" message in a footnote, explaining that week 1 is the first week of a typical flu season (which corresponds to late September 2019). This nugget of information helps a lot. We can see that the flu season peaks around week 20, and by the spring, it should be waning. Not so in 2020.

It's hard to escape the conclusion that deaths from Covid-19 are hiding inside the statistics of Pneumonia & Flu. As a statistician, I want to tell you Statistics Don't Lie! You can hide the data along one dimension, but they show up elsewhere. Misclassifying the deaths does buy someone some time. It takes a few weeks to compile all-cause mortality data (gasp, the CDC said mortality records are only 75 percent accurate after 8 weeks!)

The other small problem with the chart is the labeling. Neither axis has labels. The data label that shows up when you click on the line might be a default from the software that can't be turned off. It shows the two numbers being plotted without labels.

***

Here is a re-working of the chart that tells the story:

The proportion of deaths attributed to P&F and Covid together is roughly double the upper end of what Florida should be seeing this time of the year (without Covid). Covid-19 accounts for half the gap. The other half are still being classified as P&F. However, I suspect CDC will adjust these numbers later to reflect the reality. (In making this chart, I also learned that Florida stopped including seasonal visitors in the death counts. This is egregious manipulation. If someone died while in Florida, they should be counted. I didn't investigate whether this counting rule applies only to Covid-19 deaths, or to deaths from all causes. If they had always done that, then I might give them a pass.)

On second thought, maybe not. The other egregious thing that appeared to have happened is that the Florida state health department unplugged their prior website (https://www.floridahealth.gov) so no one can cross-reference any prior documents. The only website I can access now for Florida state health is a Covid-specific site (https://floridahealthcovid19.gov).

There must be something juicy on the previous influenza page, no?

***

Lastly, when you look at my chart, please pretend that the last week is not on there. In all likelihood, the "drop" is fake because the mortality data have not been fully updated. My chart contains one more week than the Sun Sentinel chart. So you can see that the drastic decline shown on their chart turned up a big uptick on mine (next to last week).

This is a common mistake on many charts I see these days. Half-baked numbers are shown next to fully-baked ones.

Twitter people UpSet with that Covid symptoms diagram

Been busy with an exciting project, which I might talk about one day. But I promised some people I'll follow up on Covid symptoms data visualization, so here it is.

After I posted about the Venn diagram used to depict self-reported Covid-19 symptoms by users of the Covid Symptom Tracker app (reported by Nature), Xan and a few others alerted me to Twitter discussion about alternative visualizations that people have made after they suffered the indignity of trying to parse the Venn diagram.

To avoid triggering post-trauma, for those want to view the Venn diagram, please click here.

[In the Twitter links below, you almost always have to scroll one message down - saving tweets, linking to tweets, etc. are all stuff I haven't fully figured out.]

Start with the Questions

Xan’s final comment is especially appropriate: "There's an over-riding Type-Q issue: count charts answer the wrong question".

As dataviz designers, we frequently get locked into the mindset of “what is the best way to present this dataset?” This line of thinking leads to overloaded graphics that attempt to answer every possible question that may arise from the data in one panoptic chart, akin to juggling 10 balls at once.

For complex datasets, it is often helpful to narrow down the list of questions, and provide a series of charts, each addressing one or two questions. I’ll come back to this point. I want to first show some of the nicer visuals that others have produced, which brings out the structure and complexity of this dataset.

 

The UpSet chart

The primary contender is the “UpSet” chart form, as best exemplified by Bart’s effort

The centerpiece of this chart is the matrix of dots. The horizontal rows of dots represent the presence of specific symptoms such as cough and anosmia (loss of smell and taste). The vertical columns are intuitive, once you get it. They represent combinations of symptoms, and the fill/no-fill of the dots indicates which symptoms are being combined. For example, the first column counts people reporting fatigue plus anosmia (but nothing else).

The UpSet chart clearly communicates the structure of the data. In many survey questions (including this one conducted by the Symptom Tracker app), respondents are allowed to check/tick more than one answer choices. This creates a situation where the number of answers (here, symptoms) per respondent can be zero up to the total number of answer choices.

So far, we have built a structure like we have drawn country outlines on a map. There is no data yet. The data are primarily found in the sidebar histograms (column/bar charts). Reading horizontally to the right side, one learns that the most frequently reported symptom was fatigue, covering 88 percent of the users.* Reading vertically, one learns that the top combination of symptoms was fatigue plus anosmia, covering 16 percent of users.

***

Now come the divisive acts.

Act 1: Bart orders the columns in a particular way that meets his subjective view of how he wants readers to see the data. The columns are sorted from the most frequent combinations to the least. The histogram has a “long tail”, with most of the combinations receiving a small proportion of the total. The top five combinations is where the bulk of the data is – I’d have liked to see all five columns labeled, without decimal places.

This is a choice on the part of the designer. Nils, for example, made two versions of his UpSet charts. The second version arranges the combinations from singles to quintuples.

 

Digression: The Visual in Data Visualization

The two rendering of “UpSet” charts, by Nils and Bart, is a perfect illustration of the Trifecta Checkup framework. Each corner of the Trifecta is an independent dimension, and yet all must sync. With the same data and the same question types, what differentiates the two versions is the visual design.

See how many differences you can find, and make your own design choices!

 

I place the digression here because Act 1 above has to do with the Q corner, and both visual designs can accommodate the sorting decisions. But Act 2 below pertains to the V corner.

Act 2: Bart applies a blue gradient to the matrix of dots that reinforces his subjective view about identifying frequent combinations of symptoms. Nils, by contrast, uses the matrix to show present/absent only.

I’m not sure about Act 2. I think the addition of the color gradient overloads the matrix in the chart. It has the nice effect of focusing the reader’s attention on the top 5 combinations but it also requires the reader to have understood the meaning of columns first. Perhaps applying the gradient to the histogram up top rather than the dots in the matrix can achieve the same goal with less confusion.

 

Getting Obtuse

For example, some readers (e.g. Robin) expressed confusion.

Robin is alleging something the chart doesn’t do. He pointed out (correctly) that while 16 percent experienced fatigue and anosmia only (without other symptoms), more than 50 percent reported fatigue and anosmia, plus other symptoms. That nugget of information is deeply buried inside Bart’s chart – it’s the sum of each column for which the first two dots are filled in. For example, the second column represents fatigue+anosmia+cough. So Robin wants to aggregate those up.

Robin’s critique arises from the Q(uestion) corner. If the designer wants to highlight specific combinations that occur most frequently in the data, then Bart’s encoding makes perfect sense. On the other hand, if the purpose is to highlight pairs of symptoms that occur most frequently together (disregarding symptoms outside each pair), then the data must be further aggregated. The switch in the Question requires more Data manipulation, which then affects the Visualization. That's the essence of the Trifecta Checkup framework.

Rest assured, the version that addresses Robin’s point will not give an easy answer to Bart’s question. In fact, Xan whipped up a bar chart in response:

This is actually hard to comprehend because Robin’s question is even hard to state. The first bar shows 87 percent of users reported fatigue as a symptom, the same number that appeared on Bart’s version on the right side. Then, the darkened section of the bar indicates the proportion of users who reported only fatigue and nothing else, which appears to be about 10 percent. So 1 out of 9 reported just fatigue while 8 out of 9 who reported fatigue also experienced other symptoms.

 

Xan’s bar chart can be flipped 90 degrees and replace Bart’s histogram on top of the matrix. But you see, we end up with the same problem as I mentioned up top. By jamming more insights from more questions onto the same chart, we risk dropping the other balls that were already in the air.

So, my advice is always to first winnow down the list of questions you want to address. And don’t be afraid of making a series of charts instead of one panoptic chart.

***

Act 3: Bart decides to leave out labels for the columns.

This is a curious choice given the key storyline we’ve been working with so far (the Top 5 combinations of symptoms). But notice how annoying this problem is. Combinations require long text, which must be written vertically or slanted on this design. Transposing could help but not really. It’s just a limitation of this chart form. For me, reading the filled dots underneath the columns as column labels isn’t a show-stopper.

 

Histograms vs Bar Charts

It’s worth pointing out that the sidebar “histograms” are not both histograms. I tend to think of histograms as a specific type of bar (column) chart, in which the sum of the bars (columns) can be interpreted as a whole. So all histograms are bar charts but only some bar charts are histograms.

The column chart up top is a histogram. The combinations of symptoms are disjoint, and the total of the combinations should be the total number of answer choices selected by all respondents. The bar chart on the right side however is not a histogram. Each percentage is a proportion to the whole, and adding those percentages yields way above 100%.

I like the annotation on Bart’s chart a lot. They are succinct and they give just the right information to explain how to read the chart.

 

Limitations

I already mentioned the vertical labeling issue for UpSet charts. Here are two other considerations for you.

The majority of the plotting area is dedicated to the matrix of dots. The matrix contains merely labels for data. They are like country boundaries on a map. While it lays out the structure of data very clearly, the designer should ask whether it is essential for the readers to see the entire landscape.

In real-world data, the “long tail” phenomenon we saw earlier is very common. With six featured symptoms, there are 2^6 = 64 possible combinations of symptoms (minus 1 if they filtered out those not reporting symptoms*), almost all of which will be empty. Should the low-frequency columns be removed? This is not as controversial as you think, because implicitly both Bart and Nils already dropped all empty combinations!

 

Data and Code

Kieran Healy left a comment on the last post, and you can find both the data (thank you!) and some R code for UpSet charts at his blog.

Also, Nils has a Shiny app on Github.

 

(*) One must be very careful about what “users” are being represented. They form a tiny subset of users of the Symptom Tracker app, just those who have previously taken a diagnostic test and have self-reported at least one symptom. I have separately commented on the analyses of this dataset by the team behind the app. The first post discusses their analytical methods, the second post examines how they pre-processed the data, and a future post will describe the data collection practices. For the purpose of this blog post, I’ll ignore any data issues.

(#) Bart’s chart is conceptual because some of the columns of dots are repeated, and there is one column without fills, which should have been removed by a pre-processing step applied by the research team.

Reviewing the charts in the Oxford Covid-19 study

On my sister (book) blog, I published a mega-post that examines the Oxford study that was cited two weeks ago as a counterpoint to the "doomsday" Imperial College model. These studies bring attention to the art of statistical modeling, and those six posts together are designed to give you a primer, and you don't need math to get a feel.

One aspect that didn't make it to the mega-post is the data visualization. Sad to say, the charts in the Oxford study (link) are uniformly terrible. Figure 3 is typical:

There are numerous design decisions that frustrate readers.

a) The graphic contains two charts, one on top of the other. The left axis extends floor-to-ceiling, giving the false impression that it is relevant to both charts. In fact, the graphic uses dual axes. The bottom chart references the axis shown in the bottom right corner; the left axis is meaningless. The two charts should be drawn separately.

For those who have not read the mega-post about the Oxford models, let me give a brief description of what these charts are saying. The four colors refer to four different models - these models have the same structure but different settings. The top chart shows the proportion of the population that is still susceptible to infection by a certain date. In these models, no one can get re-infected, and so you see downward curves. The bottom chart displays the growth in deaths due to Covid-19. The first death in the UK was reported on March 5.  The black dots are the official fatalities.

b) The designer allocates two-thirds of the space to the top chart, which has a much simpler message. This causes the bottom chart to be compressed beyond cognition.

c) The top chart contains just five lines, smooth curves of the same shape but different slopes. The designer chose to use thick colored lines with black outlines. As a result, nothing precise can be read from the chart. When does the yellow line start dipping? When do the two orange lines start to separate?

d) The top chart should have included margins of error. These models are very imprecise due to the sparsity of data.

e) The bottom chart should be rejected by peer reviewers. We are supposed to judge how well each of the five models fits the cumulative death counts. But three design decisions conspire to prevent us from getting the answer: (i) the vertical axis is severely compressed by tucking this chart underneath the top chart (ii) the vertical axis uses a log scale which compresses large values and (iii) the larger-than-life dots.

As I demonstrated in this post also from the sister blog, many models especially those assuming an exponential growth rate has poor fits after the first few days. Charting in log scale hides the degree of error.

f) There is a third chart squeezed into the same canvass. Notice the four little overlapping hills located around Feb 1. These hills are probability distributions, which are presented without an appropriate vertical axis. Each hill represents a particular model's estimate of the date on which the novel coronavirus entered the UK. But that date is unknowable. So the model expresses this uncertainty using a probability distribution. The "peak" of the distribution is the most likely date. The spread of the hill gives the range of plausible dates, and the height at a given date indicates the chance that that is the date of introduction. The missing axis is a probability scale, which is neither the left nor the right axis.

***

The bottom chart shows up in a slightly different form as Figure 1(A).

Here, the green, gray (blocked) and red thick lines correspond to the yellow/orange/red diamonds in Figure 3. The thin green and red lines show the margins of error I referred to above (these lines are not explicitly explained in the chart annotation.) The actual counts are shown as white rather than black diamonds.

Again, the thick lines and big diamonds conspire to swamp the gaps between model fit and actual data. Again, notice the use of a log scale. This means that the same amount of gap signifies much bigger errors as time moves to the right.

When using the log scale, we should label it using the original units. With a base 10 logarithm, the axis should have labels 1, 10, 100, 1000 instead of 0, 1, 2, 3. (This explains my previous point - why small gaps between a model line and a diamond can mean a big error as the counts go up.)

Also notice how the line of white diamonds makes it impossible to see what the models are doing prior to March 5, the date of the first reported death. The models apparently start showing fatalities prior to March 5. This is a key part of their conclusion - the Oxford team concluded that the coronavirus has been circulating in the U.K. even before the first infection was reported. The data visualization should therefore bring out the difference in timing.

I hope by the time the preprint is revised, the authors will have improved the data visualization.

 

 

 

The epidemic of simple comparisons

Another day, another Twitter user sent a sloppy chart featured on TV news. This CNN graphic comes from Hugo K. by way of Kevin T.

And it's another opportunity to apply the self-sufficiency test.

Like before, I removed the data printed on the graphic. In reading this chart, we like to know the number of U.S. reported cases of coronavirus relative to China, and Italy relative to the U.S.

So, our eyes trace these invisible lines:

U.S. cases are roughly two-thirds of China while Italian cases are 90% of U.S.

That's what the visual elements, the columns, are telling us. But it's fake news. Here is the chart with the data:

The counts of reported cases in all three countries were neck and neck around this time.

What this quick exercise shows is that anyone who correctly reads this chart is reading the data off the chart, and ignoring the contradictionary message sent by the relative column heights. Thus, the visual elements are not self-sufficient in conveying the message.

***

In a Trifecta Checkup, I'd be most concerned about the D corner. The naive comparison of these case counts is an epidemic of its own. It sometimes leads to poor decisions that can exacerbate the public-health problems. See this post on my sister blog.

The difference in case counts between different countries (or regions or cities or locales) is not a direct measure of the difference in coronavirus spread in these places! This is because there are many often-unobserved factors that will explain most if not all of the differences.

After a lot of work by epidemiologists, medical researchers, statisticians and the likes, we now realize that different places conduct different numbers of tests. No test, no positive. The U.S. has been slow to get testing ramped up.

Less understood is the effect of testing selection. Consider the U.S. where it is still hard to get tested. Only those who meet a list of criteria are eligible. Imagine an alternative reality in which the U.S. conducted the same number of tests but instead of selecting most likely infected people to be tested, we test a random sample of people. The incidence of the virus in a random sample is much lower than in the severely infected, therefore, in this new reality, the number of positives would be lower despite equal numbers of tests.

That's for equal number of tests. If test kits are readily available, then a targeted (triage) testing strategy will under-count cases since mild cases or asymptomatic infections escape attention. (See my Wired column for problems with triage.)

To complicate things even more, in most countries, the number of tests and the testing selection have changed over time so a cumulative count statistic obscures those differences.

Beside testing, there are a host of other factors that affect reported case counts. These are less talked about now but eventually will be.

Different places have different population densities. A lot of cases in a big city and an equal number of cases in a small town do not signify equal severity.  Clearly, the situation in the latter is more serious.

Because the virus affects age groups differently, a direct comparison of the case counts without adjusting for age is also misleading. The number of deaths of 80-year-olds in a college town is low not because the chance of dying from COVID-19 is lower there than in a retirement community; it's low because 80-year-olds are a small proportion of the population.

Next, the cumulative counts ignore which stage of the "epi curve" these countries are at. The following chart can replace most of the charts you're inundated with by the media:

(I found the chart here.)

An epi curve traces the time line of a disease outbreak. Every location is expected to move through stages, with cases reaching a peak and eventually the number of newly recovered will exceed the number of newly infected.

Notice that China, Italy and the US occupy different stages of this curve.  It's proper to compare U.S. to China and Italy when they were at a similar early phase of their respective epi curve.

In addition, any cross-location comparison should account for how reliable the data sources are, and the different definitions of a "case" in different locations.

***

Finally, let's consider the Question posed by the graphic designer. It is the morbid question: which country is hit the worst by coronavirus?

This is a Type DV chart. It's got a reasonable question, but the data require a lot more work to adjust for the list of biases. The visual design is hampered by the common mistake of not starting columns at zero.

 

More visuals of the economic crisis

As we move into the next phase of the dataviz bonanza arising from the coronavirus pandemic, we will see a shift from simple descriptive graphics of infections and deaths to bivariate explanatory graphics claiming (usually spurious) correlations.

The FT is leading the way with this effort, and I hope all those who follow will make a note of several wise decisions they made.

• They source their data. Most of the data about business activities come from private entities, many of which are data vendors who make money selling the data. In this article, FT got restaurant data from OpenTable, retail foot traffic data from Springboard, box office data from Box Office Mojo, flight data from Flightradar24, road traffic data from TomTom, and energy use data from European Network of Transmission System Operators for Electricity.
• They generally let the data and charts speak without "story time". The text primarily describes the trends of the various data series.
• They selected sectors that are obviously impacted by the shutdowns so any link between the observed trends and the crisis is plausible.

The FT charts are examples of clarity. Here is the one about road traffic patterns in major cities:

The cities are organized into regions: Europe, US, China, other Asia.

The key comparison is the last seven days versus the historical averages. The stories practically jump out of the page. Traffic in Paris collapsed on Tuesday. Wuhan is still locked down despite the falloff in infections. Drivers of Tokyo are probably wondering why teams are not going to the Olympics this year. Londoners? My guess is they're determined to not let another Brexit deadline slip.

***

I'd hope we go even further than FT when publishing this type of visual analytics involving "Big Data." These business data obtained from private sources typically have OCCAM properties: they are observational, seemingly complete, uncontrolled, adapted and merged. All these properties make the data very challenging to interpret.

The coronavirus case and death counts are simple by comparison. People are now aware of all the problems from differential rates of testing to which groups are selectively tested (i.e. triage) to how an infection or death is defined. The problems involving Big Data are much more complex.

I have three additional proposals:

Disclosure of Biases and Limitations

The private data have many more potential pitfalls. Take OpenTable data for example. The data measure restaurant bookings, not revenues. It measures gross bookings, not net bookings (i.e. removing no-shows). Only a proportion of restaurants use OpenTable (which cost owners money). OpenTable does not strike me as a quasi-monopoly so there are competitors with significant market share. The restaurants that use OpenTable do not form a random subsample of all restaurants. One of the most popular restaurants in the U.S. are pizza joints, with little of no seating, which do not feature in the bookings data. OpenTable also has differential popularity by country, region, or probably cuisine. 

I believe data journalists ought to provide such context in a footnote. Readers should have the information to judge whether they believe the data are sufficiently representative. Private data vendors who want data journalists to feature their datasets should be required to supply a footnote that describes the biases and limitations of their data.

Data journalists should think seriously about how they headline this type of chart. The standard practice is what FT adopted. The headline said "Restaurant bookings have collapsed" with a small footnote saying "Source: OpenTable". Should the headline have said "OpenTable bookings have collapsed" instead?

Disclosure of Definitions and Proxies

In the road traffic chart shown above, the metric is called "TomTom traffic congestion index". In order to earn this free advertising (euphemistically called "earned media" by industry), TomTom should be obliged to explain how this index is constructed. What does index = 100 mean?

[For example, it is curious that the Madrid index values are much lower across the board than those in Paris and Roma.]

For the electric usage chart, FT discloses the name of the data provider as a group of "43 electricity transmission system operators in 36 countries across Europe." Now, that is important context but can be better. The group may consist of 43 operators but how many of them are in the dataset? What proportion of the total electric usage do they account for in each country? If they have low penetration in a particular country, do they just report the low statistics or adjust the numbres?

If the journalist decides to use a proxy, for example, OpenTable restaurant bookings to reflect restaurant revenues, that should be explained, perhaps even justified.

Data as a Public Good

If private businesses choose to supply data to media outlets as a public service, they should allow the underlying data to be published.

Speaking from experience, I've seen a lot of bad data. It's one thing to hold your nose when the data are analyzed to make online advertising more profitable, or to find signals to profit from the stock market. It's another thing for the data analysis to drive public policy, in this case, policies that will have life-or-death implications.

All these charts lament the high prices charged by U.S. hospitals

A former student asked me about this chart from the New York Times that highlights much higher prices of hospital procedures in the U.S. relative to a comparison group of seven countries.

The dot plot is clearly thought through. It is not a default chart that pops out of software.

Based on its design, we surmise that the designer has the following intentions:

1. The names of the medical procedures are printed to be read, thus the long text is placed horizontally.
   
   
2. The actual price is not as important as the relative price, expressed as an index with the U.S. price at 100%. These reference values are printed in glaring red, unignorable.
   
   
3. Notwithstanding the above point, the actual price is still of secondary importance, and the values are provided as a supplement to the row labels. Getting to the actual prices in the comparison countries requires further effort, and a calculator.
   
   
4. The primary comparison is between the U.S. and the rest of the world (or the group of seven countries included). It is less important to distinguish specific countries in the comparison group, and thus the non-U.S. dots are given pastels that take some effort to differentiate.
   
   
5. Probably due to reader feedback, the font size is subject to a minimum so that some labels are split into two lines to prevent the text from dominating the plotting region.

***

In the Trifecta Checkup view of the world, there is no single best design. The best design depends on the intended message and what’s in the available data.

To illustate this, I will present a few variants of the above design, and discuss how these alternative designs reflect the designer's intentions.

Note that in all my charts, I expressed the relative price in terms of discounts, which is the mirror image of premiums. Instead of saying Country A's price is 80% of the U.S. price, I prefer to say Country A's price is a 20% saving (or discount) off the U.S. price.

First up is the following chart that emphasizes countries instead of hospital procedures:

This chart encourages readers to draw conclusions such as "Hospital prices are 60-80 percent cheaper in Holland relative to the U.S." But it is more taxing to compare the cost of a specific procedure across countries.

The indexing strategy already creates a barrier to understanding relative costs of a specific procedure. For example, the value for angioplasty in Australia is about 55% and in Switzerland, about 75%. The difference 75%-55% is meaningless because both numbers are relative savings from the U.S. baseline. Comparing Australia and Switzerland requires a ratio (0.75/0.55 = 1.36): Australia's prices are 36% above Swiss prices, or alternatively, Swiss prices are a 64% 26% discount off Australia's prices.

The following design takes it even further, excluding details of individual procedures:

For some readers, less is more. It’s even easier to get a rough estimate of how much cheaper prices are in the comparison countries, for now, except for two “outliers”, the chart does not display individual values.

The widths of these bars reveal that in some countries, the amount of savings depends on the specific procedures.

The bar design releases the designer from a horizontal orientation. The country labels are shorter and can be placed at the bottom in a vertical design:

It's not that one design is obviously superior to the others. Each version does some things better. A good designer recognizes the strengths and weaknesses of each design, and selects one to fulfil his/her intentions.

 

P.S. [1/3/20] Corrected a computation, explained in Ken's comment.

Marketers want millennials to know they're millennials

When I posted about the lack of a standard definition of "millennials", Dean Eckles tweeted about the arbitrary division of age into generational categories. His view is further reinforced by the following chart, courtesy of PewResearch by way of MarketingCharts.com.

Pew asked people what generation they belong to. The amount of people who fail to place themselves in the right category is remarkable. One way to interpret this finding is that these are marketing categories created by the marketing profession. We learned in my other post that even people who use the term millennial do not have a consensus definition of it. Perhaps the 8 percent of "millennials" who identify as "boomers" are handing in a protest vote!

The chart is best read row by row - the use of stacked bar charts provides a clue. Forty percent of millennials identified as millennials, which leaves sixty percent identifying as some other generation (with about 5 percent indicating "other" responses). 

While this chart is not pretty, and may confuse some readers, it actually shows a healthy degree of analytical thinking. Arranging for the row-first interpretation is a good start. The designer also realizes the importance of the diagonal entries - what proportion of each generation self-identify as a member of that generation. Dotted borders are deployed to draw eyes to the diagonal.

***

The design doesn't do full justice for the analytical intelligence. Despite the use of the bar chart form, readers may be tempted to read column by column due to the color scheme. The chart doesn't have an easy column-by-column interpretation.

It's not obvious which axis has the true category and which, the self-identified category. The designer adds a hint in the sub-title to counteract this problem.

Finally, the dotted borders are no match for the differential colors. So a key message of the chart is buried.

Here is a revised chart, using a grouped bar chart format:

***

In a Trifecta checkup (link), the original chart is a Type V chart. It addresses a popular, pertinent question, and it shows mature analytical thinking but the visual design does not do full justice to the data story.